Feature detection from local energy
Pattern Recognition Letters
Algorithms for clustering data
Algorithms for clustering data
On the classification of image features
Pattern Recognition Letters
Performance of optical flow techniques
International Journal of Computer Vision
What is the goal of sensory coding?
Neural Computation
Geodesic Active Contours and Level Sets for the Detection and Tracking of Moving Objects
IEEE Transactions on Pattern Analysis and Machine Intelligence
Measurement of Image Velocity
Temporal spatio-velocity transform and its application to tracking and interaction
Computer Vision and Image Understanding - Special issue on event detection in video
An iterative region-growing algorithm for motion segmentation and estimation: Research Articles
International Journal of Intelligent Systems - Robotics and Computer Vision
Data-driven synthesis of composite-feature detectors for 3D image analysis
Image and Vision Computing
3D-orientation space: filters and sampling
SCIA'03 Proceedings of the 13th Scandinavian conference on Image analysis
Fast occluded object tracking by a robust appearance filter
IEEE Transactions on Pattern Analysis and Machine Intelligence
| Hi-index | 0.00 |
Motion estimation by means of spatio-temporal energy filters –velocity tuned filters– is known to be robust to noise and aliasing and to allow an easy treatment of the aperture problem. In this paper we propose a motion representation based on the composition of spatio-temporal energy features, i.e., responses of a set of filters in phase quadrature tuned to different scales and orientations. Complex motion patterns are identified by unsupervised cluster analysis of energy features. The integration criterion reflects the degree of alignment of maxima of the features's amplitude, which is related to phase congruence. The composite-feature representation has been applied to motion segmentation with a geodesic active model both for initialization and image potential definition. We will show that the resulting method is able to handle typical problems, such as partial and total occlusions, large inter-frame displacements, moving background and noise.